The repository collects many various multi-modal transformer architectures, including image transformer, video transformer, image-language transformer, video-language transformer and self-supervised learning models. Additionally, it also collects many useful tutorials and tools in these related domains.

Auto torch image models: train and evaluation

This repository contains an advanced face recognition solution that uses the Swin Transformer model for feature extraction and an SVM classifier for identifying individuals.

An aware attention free simplified image transformer

Example application for training Microsofts's pretrained BEiT image transformer model on a new image classification task

A transformer based on source keypoints and target keypoints